diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries/iommu.c')
-rw-r--r-- | arch/powerpc/platforms/pseries/iommu.c | 882 |
1 files changed, 615 insertions, 267 deletions
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 2e0a8eab5588..561adac69022 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -39,28 +39,45 @@ #include "pseries.h" -static struct iommu_table_group *iommu_pseries_alloc_group(int node) +enum { + DDW_QUERY_PE_DMA_WIN = 0, + DDW_CREATE_PE_DMA_WIN = 1, + DDW_REMOVE_PE_DMA_WIN = 2, + + DDW_APPLICABLE_SIZE +}; + +enum { + DDW_EXT_SIZE = 0, + DDW_EXT_RESET_DMA_WIN = 1, + DDW_EXT_QUERY_OUT_SIZE = 2 +}; + +static struct iommu_table *iommu_pseries_alloc_table(int node) { - struct iommu_table_group *table_group; struct iommu_table *tbl; - table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL, - node); - if (!table_group) - return NULL; - tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, node); if (!tbl) - goto free_group; + return NULL; INIT_LIST_HEAD_RCU(&tbl->it_group_list); kref_init(&tbl->it_kref); + return tbl; +} - table_group->tables[0] = tbl; +static struct iommu_table_group *iommu_pseries_alloc_group(int node) +{ + struct iommu_table_group *table_group; + + table_group = kzalloc_node(sizeof(*table_group), GFP_KERNEL, node); + if (!table_group) + return NULL; - return table_group; + table_group->tables[0] = iommu_pseries_alloc_table(node); + if (table_group->tables[0]) + return table_group; -free_group: kfree(table_group); return NULL; } @@ -93,6 +110,8 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, u64 proto_tce; __be64 *tcep; u64 rpn; + const unsigned long tceshift = tbl->it_page_shift; + const unsigned long pagesize = IOMMU_PAGE_SIZE(tbl); proto_tce = TCE_PCI_READ; // Read allowed @@ -103,10 +122,10 @@ static int tce_build_pSeries(struct iommu_table *tbl, long index, while (npages--) { /* can't move this out since we might cross MEMBLOCK boundary */ - rpn = __pa(uaddr) >> TCE_SHIFT; - *tcep = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); + rpn = __pa(uaddr) >> tceshift; + *tcep = cpu_to_be64(proto_tce | rpn << tceshift); - uaddr += TCE_PAGE_SIZE; + uaddr += pagesize; tcep++; } return 0; @@ -132,7 +151,7 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index) return be64_to_cpu(*tcep); } -static void tce_free_pSeriesLP(unsigned long liobn, long, long); +static void tce_free_pSeriesLP(unsigned long liobn, long, long, long); static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long); static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, @@ -152,12 +171,12 @@ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, proto_tce |= TCE_PCI_WRITE; while (npages--) { - tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift; + tce = proto_tce | rpn << tceshift; rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce); if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { ret = (int)rc; - tce_free_pSeriesLP(liobn, tcenum_start, + tce_free_pSeriesLP(liobn, tcenum_start, tceshift, (npages_start - (npages + 1))); break; } @@ -191,10 +210,11 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long tcenum_start = tcenum, npages_start = npages; int ret = 0; unsigned long flags; + const unsigned long tceshift = tbl->it_page_shift; if ((npages == 1) || !firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) { return tce_build_pSeriesLP(tbl->it_index, tcenum, - tbl->it_page_shift, npages, uaddr, + tceshift, npages, uaddr, direction, attrs); } @@ -211,13 +231,13 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, if (!tcep) { local_irq_restore(flags); return tce_build_pSeriesLP(tbl->it_index, tcenum, - tbl->it_page_shift, + tceshift, npages, uaddr, direction, attrs); } __this_cpu_write(tce_page, tcep); } - rpn = __pa(uaddr) >> TCE_SHIFT; + rpn = __pa(uaddr) >> tceshift; proto_tce = TCE_PCI_READ; if (direction != DMA_TO_DEVICE) proto_tce |= TCE_PCI_WRITE; @@ -231,12 +251,12 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, limit = min_t(long, npages, 4096/TCE_ENTRY_SIZE); for (l = 0; l < limit; l++) { - tcep[l] = cpu_to_be64(proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT); + tcep[l] = cpu_to_be64(proto_tce | rpn << tceshift); rpn++; } rc = plpar_tce_put_indirect((u64)tbl->it_index, - (u64)tcenum << 12, + (u64)tcenum << tceshift, (u64)__pa(tcep), limit); @@ -263,12 +283,13 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, return ret; } -static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages) +static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, + long npages) { u64 rc; while (npages--) { - rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0); + rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, 0); if (rc && printk_ratelimit()) { printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc); @@ -287,9 +308,11 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n u64 rc; if (!firmware_has_feature(FW_FEATURE_STUFF_TCE)) - return tce_free_pSeriesLP(tbl->it_index, tcenum, npages); + return tce_free_pSeriesLP(tbl->it_index, tcenum, + tbl->it_page_shift, npages); - rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages); + rc = plpar_tce_stuff((u64)tbl->it_index, + (u64)tcenum << tbl->it_page_shift, 0, npages); if (rc && printk_ratelimit()) { printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n"); @@ -305,7 +328,8 @@ static unsigned long tce_get_pSeriesLP(struct iommu_table *tbl, long tcenum) u64 rc; unsigned long tce_ret; - rc = plpar_tce_get((u64)tbl->it_index, (u64)tcenum << 12, &tce_ret); + rc = plpar_tce_get((u64)tbl->it_index, + (u64)tcenum << tbl->it_page_shift, &tce_ret); if (rc && printk_ratelimit()) { printk("tce_get_pSeriesLP: plpar_tce_get failed. rc=%lld\n", rc); @@ -325,7 +349,7 @@ struct dynamic_dma_window_prop { __be32 window_shift; /* ilog2(tce_window_size) */ }; -struct direct_window { +struct dma_win { struct device_node *device; const struct dynamic_dma_window_prop *prop; struct list_head list; @@ -334,7 +358,7 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { u32 windows_available; - u32 largest_available_block; + u64 largest_available_block; u32 page_size; u32 migration_capable; }; @@ -345,12 +369,13 @@ struct ddw_create_response { u32 addr_lo; }; -static LIST_HEAD(direct_window_list); +static LIST_HEAD(dma_win_list); /* prevents races between memory on/offline and window creation */ -static DEFINE_SPINLOCK(direct_window_list_lock); +static DEFINE_SPINLOCK(dma_win_list_lock); /* protects initializing window twice for same device */ -static DEFINE_MUTEX(direct_window_init_mutex); +static DEFINE_MUTEX(dma_win_init_mutex); #define DIRECT64_PROPNAME "linux,direct64-ddr-window-info" +#define DMA64_PROPNAME "linux,dma64-ddr-window-info" static int tce_clearrange_multi_pSeriesLP(unsigned long start_pfn, unsigned long num_pfn, const void *arg) @@ -477,6 +502,24 @@ static int tce_setrange_multi_pSeriesLP_walk(unsigned long start_pfn, return tce_setrange_multi_pSeriesLP(start_pfn, num_pfn, arg); } +static void iommu_table_setparms_common(struct iommu_table *tbl, unsigned long busno, + unsigned long liobn, unsigned long win_addr, + unsigned long window_size, unsigned long page_shift, + void *base, struct iommu_table_ops *table_ops) +{ + tbl->it_busno = busno; + tbl->it_index = liobn; + tbl->it_offset = win_addr >> page_shift; + tbl->it_size = window_size >> page_shift; + tbl->it_page_shift = page_shift; + tbl->it_base = (unsigned long)base; + tbl->it_blocksize = 16; + tbl->it_type = TCE_PCI; + tbl->it_ops = table_ops; +} + +struct iommu_table_ops iommu_table_pseries_ops; + static void iommu_table_setparms(struct pci_controller *phb, struct device_node *dn, struct iommu_table *tbl) @@ -485,8 +528,13 @@ static void iommu_table_setparms(struct pci_controller *phb, const unsigned long *basep; const u32 *sizep; - node = phb->dn; + /* Test if we are going over 2GB of DMA space */ + if (phb->dma_window_base_cur + phb->dma_window_size > SZ_2G) { + udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); + panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); + } + node = phb->dn; basep = of_get_property(node, "linux,tce-base", NULL); sizep = of_get_property(node, "linux,tce-size", NULL); if (basep == NULL || sizep == NULL) { @@ -495,33 +543,18 @@ static void iommu_table_setparms(struct pci_controller *phb, return; } - tbl->it_base = (unsigned long)__va(*basep); + iommu_table_setparms_common(tbl, phb->bus->number, 0, phb->dma_window_base_cur, + phb->dma_window_size, IOMMU_PAGE_SHIFT_4K, + __va(*basep), &iommu_table_pseries_ops); if (!is_kdump_kernel()) memset((void *)tbl->it_base, 0, *sizep); - tbl->it_busno = phb->bus->number; - tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; - - /* Units of tce entries */ - tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift; - - /* Test if we are going over 2GB of DMA space */ - if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) { - udbg_printf("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); - panic("PCI_DMA: Unexpected number of IOAs under this PHB.\n"); - } - phb->dma_window_base_cur += phb->dma_window_size; - - /* Set the tce table size - measured in entries */ - tbl->it_size = phb->dma_window_size >> tbl->it_page_shift; - - tbl->it_index = 0; - tbl->it_blocksize = 16; - tbl->it_type = TCE_PCI; } +struct iommu_table_ops iommu_table_lpar_multi_ops; + /* * iommu_table_setparms_lpar * @@ -533,17 +566,13 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb, struct iommu_table_group *table_group, const __be32 *dma_window) { - unsigned long offset, size; + unsigned long offset, size, liobn; - of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size); + of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); + + iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, + &iommu_table_lpar_multi_ops); - tbl->it_busno = phb->bus->number; - tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K; - tbl->it_base = 0; - tbl->it_blocksize = 16; - tbl->it_type = TCE_PCI; - tbl->it_offset = offset >> tbl->it_page_shift; - tbl->it_size = size >> tbl->it_page_shift; table_group->tce32_start = offset; table_group->tce32_size = size; @@ -623,8 +652,9 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) tbl = pci->table_group->tables[0]; iommu_table_setparms(pci->phb, dn, tbl); - tbl->it_ops = &iommu_table_pseries_ops; - iommu_init_table(tbl, pci->phb->node, 0, 0); + + if (!iommu_init_table(tbl, pci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); /* Divide the rest (1.75GB) among the children */ pci->phb->dma_window_size = 0x80000000ul; @@ -636,8 +666,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) #ifdef CONFIG_IOMMU_API static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned - long *tce, enum dma_data_direction *direction, - bool realmode) + long *tce, enum dma_data_direction *direction) { long rc; unsigned long ioba = (unsigned long) index << tbl->it_page_shift; @@ -671,6 +700,33 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { .get = tce_get_pSeriesLP }; +/* + * Find nearest ibm,dma-window (default DMA window) or direct DMA window or + * dynamic 64bit DMA window, walking up the device tree. + */ +static struct device_node *pci_dma_find(struct device_node *dn, + const __be32 **dma_window) +{ + const __be32 *dw = NULL; + + for ( ; dn && PCI_DN(dn); dn = dn->parent) { + dw = of_get_property(dn, "ibm,dma-window", NULL); + if (dw) { + if (dma_window) + *dma_window = dw; + return dn; + } + dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (dw) + return dn; + dw = of_get_property(dn, DMA64_PROPNAME, NULL); + if (dw) + return dn; + } + + return NULL; +} + static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) { struct iommu_table *tbl; @@ -683,17 +739,10 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - /* Find nearest ibm,dma-window, walking up the device tree */ - for (pdn = dn; pdn != NULL; pdn = pdn->parent) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - if (dma_window != NULL) - break; - } + pdn = pci_dma_find(dn, &dma_window); - if (dma_window == NULL) { + if (dma_window == NULL) pr_debug(" no ibm,dma-window property !\n"); - return; - } ppci = PCI_DN(pdn); @@ -703,10 +752,13 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window); - tbl->it_ops = &iommu_table_lpar_multi_ops; - iommu_init_table(tbl, ppci->phb->node, 0, 0); + if (dma_window) { + iommu_table_setparms_lpar(ppci->phb, pdn, tbl, + ppci->table_group, dma_window); + + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + } iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -734,8 +786,10 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node); tbl = PCI_DN(dn)->table_group->tables[0]; iommu_table_setparms(phb, dn, tbl); - tbl->it_ops = &iommu_table_pseries_ops; - iommu_init_table(tbl, phb->node, 0, 0); + + if (!iommu_init_table(tbl, phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + set_iommu_table_base(&dev->dev, tbl); return; } @@ -767,28 +821,10 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static void remove_ddw(struct device_node *np, bool remove_prop) +static void clean_dma_window(struct device_node *np, struct dynamic_dma_window_prop *dwp) { - struct dynamic_dma_window_prop *dwp; - struct property *win64; - u32 ddw_avail[3]; - u64 liobn; - int ret = 0; - - ret = of_property_read_u32_array(np, "ibm,ddw-applicable", - &ddw_avail[0], 3); - - win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); - if (!win64) - return; - - if (ret || win64->length < sizeof(*dwp)) - goto delprop; - - dwp = win64->value; - liobn = (u64)be32_to_cpu(dwp->liobn); + int ret; - /* clear the whole window, note the arg is in kernel pages */ ret = tce_clearrange_multi_pSeriesLP(0, 1ULL << (be32_to_cpu(dwp->window_shift) - PAGE_SHIFT), dwp); if (ret) @@ -797,86 +833,199 @@ static void remove_ddw(struct device_node *np, bool remove_prop) else pr_debug("%pOF successfully cleared tces in window.\n", np); +} + +/* + * Call only if DMA window is clean. + */ +static void __remove_dma_window(struct device_node *np, u32 *ddw_avail, u64 liobn) +{ + int ret; - ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); + ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn); if (ret) - pr_warn("%pOF: failed to remove direct window: rtas returned " + pr_warn("%pOF: failed to remove DMA window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); else - pr_debug("%pOF: successfully removed direct window: rtas returned " + pr_debug("%pOF: successfully removed DMA window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); +} + +static void remove_dma_window(struct device_node *np, u32 *ddw_avail, + struct property *win) +{ + struct dynamic_dma_window_prop *dwp; + u64 liobn; -delprop: - if (remove_prop) - ret = of_remove_property(np, win64); + dwp = win->value; + liobn = (u64)be32_to_cpu(dwp->liobn); + + clean_dma_window(np, dwp); + __remove_dma_window(np, ddw_avail, liobn); +} + +static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_name) +{ + struct property *win; + u32 ddw_avail[DDW_APPLICABLE_SIZE]; + int ret = 0; + + win = of_find_property(np, win_name, NULL); + if (!win) + return -EINVAL; + + ret = of_property_read_u32_array(np, "ibm,ddw-applicable", + &ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) - pr_warn("%pOF: failed to remove direct window property: %d\n", + return 0; + + + if (win->length >= sizeof(struct dynamic_dma_window_prop)) + remove_dma_window(np, ddw_avail, win); + + if (!remove_prop) + return 0; + + ret = of_remove_property(np, win); + if (ret) + pr_warn("%pOF: failed to remove DMA window property: %d\n", np, ret); + return 0; } -static u64 find_existing_ddw(struct device_node *pdn) +static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift) { - struct direct_window *window; - const struct dynamic_dma_window_prop *direct64; - u64 dma_addr = 0; + struct dma_win *window; + const struct dynamic_dma_window_prop *dma64; + bool found = false; - spin_lock(&direct_window_list_lock); + spin_lock(&dma_win_list_lock); /* check if we already created a window and dupe that config if so */ - list_for_each_entry(window, &direct_window_list, list) { + list_for_each_entry(window, &dma_win_list, list) { if (window->device == pdn) { - direct64 = window->prop; - dma_addr = be64_to_cpu(direct64->dma_base); + dma64 = window->prop; + *dma_addr = be64_to_cpu(dma64->dma_base); + *window_shift = be32_to_cpu(dma64->window_shift); + found = true; break; } } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); - return dma_addr; + return found; } -static int find_existing_ddw_windows(void) +static struct dma_win *ddw_list_new_entry(struct device_node *pdn, + const struct dynamic_dma_window_prop *dma64) +{ + struct dma_win *window; + + window = kzalloc(sizeof(*window), GFP_KERNEL); + if (!window) + return NULL; + + window->device = pdn; + window->prop = dma64; + + return window; +} + +static void find_existing_ddw_windows_named(const char *name) { int len; struct device_node *pdn; - struct direct_window *window; - const struct dynamic_dma_window_prop *direct64; - - if (!firmware_has_feature(FW_FEATURE_LPAR)) - return 0; + struct dma_win *window; + const struct dynamic_dma_window_prop *dma64; - for_each_node_with_property(pdn, DIRECT64_PROPNAME) { - direct64 = of_get_property(pdn, DIRECT64_PROPNAME, &len); - if (!direct64) + for_each_node_with_property(pdn, name) { + dma64 = of_get_property(pdn, name, &len); + if (!dma64 || len < sizeof(*dma64)) { + remove_ddw(pdn, true, name); continue; + } - window = kzalloc(sizeof(*window), GFP_KERNEL); - if (!window || len < sizeof(struct dynamic_dma_window_prop)) { - kfree(window); - remove_ddw(pdn, true); - continue; + window = ddw_list_new_entry(pdn, dma64); + if (!window) { + of_node_put(pdn); + break; } - window->device = pdn; - window->prop = direct64; - spin_lock(&direct_window_list_lock); - list_add(&window->list, &direct_window_list); - spin_unlock(&direct_window_list_lock); + spin_lock(&dma_win_list_lock); + list_add(&window->list, &dma_win_list); + spin_unlock(&dma_win_list_lock); } +} + +static int find_existing_ddw_windows(void) +{ + if (!firmware_has_feature(FW_FEATURE_LPAR)) + return 0; + + find_existing_ddw_windows_named(DIRECT64_PROPNAME); + find_existing_ddw_windows_named(DMA64_PROPNAME); return 0; } machine_arch_initcall(pseries, find_existing_ddw_windows); +/** + * ddw_read_ext - Get the value of an DDW extension + * @np: device node from which the extension value is to be read. + * @extnum: index number of the extension. + * @value: pointer to return value, modified when extension is available. + * + * Checks if "ibm,ddw-extensions" exists for this node, and get the value + * on index 'extnum'. + * It can be used only to check if a property exists, passing value == NULL. + * + * Returns: + * 0 if extension successfully read + * -EINVAL if the "ibm,ddw-extensions" does not exist, + * -ENODATA if "ibm,ddw-extensions" does not have a value, and + * -EOVERFLOW if "ibm,ddw-extensions" does not contain this extension. + */ +static inline int ddw_read_ext(const struct device_node *np, int extnum, + u32 *value) +{ + static const char propname[] = "ibm,ddw-extensions"; + u32 count; + int ret; + + ret = of_property_read_u32_index(np, propname, DDW_EXT_SIZE, &count); + if (ret) + return ret; + + if (count < extnum) + return -EOVERFLOW; + + if (!value) + value = &count; + + return of_property_read_u32_index(np, propname, extnum, value); +} + static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, - struct ddw_query_response *query) + struct ddw_query_response *query, + struct device_node *parent) { struct device_node *dn; struct pci_dn *pdn; - u32 cfg_addr; + u32 cfg_addr, ext_query, query_out[5]; u64 buid; - int ret; + int ret, out_sz; + + /* + * From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can rule how many + * output parameters ibm,query-pe-dma-windows will have, ranging from + * 5 to 6. + */ + ret = ddw_read_ext(parent, DDW_EXT_QUERY_OUT_SIZE, &ext_query); + if (!ret && ext_query == 1) + out_sz = 6; + else + out_sz = 5; /* * Get the config address and phb buid of the PE window. @@ -889,11 +1038,30 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, buid = pdn->phb->buid; cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); - ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, - cfg_addr, BUID_HI(buid), BUID_LO(buid)); - dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x" - " returned %d\n", ddw_avail[0], cfg_addr, BUID_HI(buid), - BUID_LO(buid), ret); + ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out, + cfg_addr, BUID_HI(buid), BUID_LO(buid)); + + switch (out_sz) { + case 5: + query->windows_available = query_out[0]; + query->largest_available_block = query_out[1]; + query->page_size = query_out[2]; + query->migration_capable = query_out[3]; + break; + case 6: + query->windows_available = query_out[0]; + query->largest_available_block = ((u64)query_out[1] << 32) | + query_out[2]; + query->page_size = query_out[3]; + query->migration_capable = query_out[4]; + break; + } + + dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d, lb=%llx ps=%x wn=%d\n", + ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid), + BUID_LO(buid), ret, query->largest_available_block, + query->page_size, query->windows_available); + return ret; } @@ -920,15 +1088,16 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ - ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, - cfg_addr, BUID_HI(buid), BUID_LO(buid), - page_shift, window_shift); + ret = rtas_call(ddw_avail[DDW_CREATE_PE_DMA_WIN], 5, 4, + (u32 *)create, cfg_addr, BUID_HI(buid), + BUID_LO(buid), page_shift, window_shift); } while (rtas_busy_delay(ret)); dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " - "(liobn = 0x%x starting addr = %x %x)\n", ddw_avail[1], - cfg_addr, BUID_HI(buid), BUID_LO(buid), page_shift, - window_shift, ret, create->liobn, create->addr_hi, create->addr_lo); + "(liobn = 0x%x starting addr = %x %x)\n", + ddw_avail[DDW_CREATE_PE_DMA_WIN], cfg_addr, BUID_HI(buid), + BUID_LO(buid), page_shift, window_shift, ret, create->liobn, + create->addr_hi, create->addr_lo); return ret; } @@ -969,6 +1138,94 @@ static phys_addr_t ddw_memory_hotplug_max(void) } /* + * Platforms supporting the DDW option starting with LoPAR level 2.7 implement + * ibm,ddw-extensions, which carries the rtas token for + * ibm,reset-pe-dma-windows. + * That rtas-call can be used to restore the default DMA window for the device. + */ +static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn) +{ + int ret; + u32 cfg_addr, reset_dma_win; + u64 buid; + struct device_node *dn; + struct pci_dn *pdn; + + ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win); + if (ret) + return; + + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8); + + ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid), + BUID_LO(buid)); + if (ret) + dev_info(&dev->dev, + "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ", + reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid), + ret); +} + +/* Return largest page shift based on "IO Page Sizes" output of ibm,query-pe-dma-window. */ +static int iommu_get_page_shift(u32 query_page_size) +{ + /* Supported IO page-sizes according to LoPAR, note that 2M is out of order */ + const int shift[] = { + __builtin_ctzll(SZ_4K), __builtin_ctzll(SZ_64K), __builtin_ctzll(SZ_16M), + __builtin_ctzll(SZ_32M), __builtin_ctzll(SZ_64M), __builtin_ctzll(SZ_128M), + __builtin_ctzll(SZ_256M), __builtin_ctzll(SZ_16G), __builtin_ctzll(SZ_2M) + }; + + int i = ARRAY_SIZE(shift) - 1; + int ret = 0; + + /* + * On LoPAR, ibm,query-pe-dma-window outputs "IO Page Sizes" using a bit field: + * - bit 31 means 4k pages are supported, + * - bit 30 means 64k pages are supported, and so on. + * Larger pagesizes map more memory with the same amount of TCEs, so start probing them. + */ + for (; i >= 0 ; i--) { + if (query_page_size & (1 << i)) + ret = max(ret, shift[i]); + } + + return ret; +} + +static struct property *ddw_property_create(const char *propname, u32 liobn, u64 dma_addr, + u32 page_shift, u32 window_shift) +{ + struct dynamic_dma_window_prop *ddwprop; + struct property *win64; + + win64 = kzalloc(sizeof(*win64), GFP_KERNEL); + if (!win64) + return NULL; + + win64->name = kstrdup(propname, GFP_KERNEL); + ddwprop = kzalloc(sizeof(*ddwprop), GFP_KERNEL); + win64->value = ddwprop; + win64->length = sizeof(*ddwprop); + if (!win64->name || !win64->value) { + kfree(win64->name); + kfree(win64->value); + kfree(win64); + return NULL; + } + + ddwprop->liobn = cpu_to_be32(liobn); + ddwprop->dma_base = cpu_to_be64(dma_addr); + ddwprop->tce_shift = cpu_to_be32(page_shift); + ddwprop->window_shift = cpu_to_be32(window_shift); + + return win64; +} + +/* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, * and record the dma-offset in the struct device. @@ -977,27 +1234,37 @@ static phys_addr_t ddw_memory_hotplug_max(void) * pdn: the parent pe node with the ibm,dma_window property * Future: also check if we can remap the base window for our base page size * - * returns the dma offset for use by the direct mapped DMA code. + * returns true if can map all pages (direct mapping), false otherwise.. */ -static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) +static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) { - int len, ret; + int len = 0, ret; + int max_ram_len = order_base_2(ddw_memory_hotplug_max()); struct ddw_query_response query; struct ddw_create_response create; int page_shift; - u64 dma_addr, max_addr; + u64 win_addr; + const char *win_name; struct device_node *dn; - u32 ddw_avail[3]; - struct direct_window *window; + u32 ddw_avail[DDW_APPLICABLE_SIZE]; + struct dma_win *window; struct property *win64; - struct dynamic_dma_window_prop *ddwprop; struct failed_ddw_pdn *fpdn; + bool default_win_removed = false, direct_mapping = false; + bool pmem_present; + struct pci_dn *pci = PCI_DN(pdn); + struct property *default_win = NULL; - mutex_lock(&direct_window_init_mutex); + dn = of_find_node_by_type(NULL, "ibm,pmemory"); + pmem_present = dn != NULL; + of_node_put(dn); - dma_addr = find_existing_ddw(pdn); - if (dma_addr != 0) + mutex_lock(&dma_win_init_mutex); + + if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) { + direct_mapping = (len >= max_ram_len); goto out_unlock; + } /* * If we already went through this for a previous function of @@ -1020,7 +1287,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * the property is actually in the parent, not the PE */ ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable", - &ddw_avail[0], 3); + &ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) goto out_failed; @@ -1031,108 +1298,194 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * of page sizes: supported and supported for migrate-dma. */ dn = pci_device_to_OF_node(dev); - ret = query_ddw(dev, ddw_avail, &query); + ret = query_ddw(dev, ddw_avail, &query, pdn); if (ret != 0) goto out_failed; + /* + * If there is no window available, remove the default DMA window, + * if it's present. This will make all the resources available to the + * new DDW window. + * If anything fails after this, we need to restore it, so also check + * for extensions presence. + */ if (query.windows_available == 0) { - /* - * no additional windows are available for this device. - * We might be able to reallocate the existing window, - * trading in for a larger page size. - */ - dev_dbg(&dev->dev, "no free dynamic windows"); - goto out_failed; - } - if (query.page_size & 4) { - page_shift = 24; /* 16MB */ - } else if (query.page_size & 2) { - page_shift = 16; /* 64kB */ - } else if (query.page_size & 1) { - page_shift = 12; /* 4kB */ - } else { - dev_dbg(&dev->dev, "no supported direct page size in mask %x", - query.page_size); - goto out_failed; + int reset_win_ext; + + /* DDW + IOMMU on single window may fail if there is any allocation */ + if (iommu_table_in_use(pci->table_group->tables[0])) { + dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n"); + goto out_failed; + } + + default_win = of_find_property(pdn, "ibm,dma-window", NULL); + if (!default_win) + goto out_failed; + + reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL); + if (reset_win_ext) + goto out_failed; + + remove_dma_window(pdn, ddw_avail, default_win); + default_win_removed = true; + + /* Query again, to check if the window is available */ + ret = query_ddw(dev, ddw_avail, &query, pdn); + if (ret != 0) + goto out_failed; + + if (query.windows_available == 0) { + /* no windows are available for this device. */ + dev_dbg(&dev->dev, "no free dynamic windows"); + goto out_failed; + } } - /* verify the window * number of ptes will map the partition */ - /* check largest block * page size > max memory hotplug addr */ - max_addr = ddw_memory_hotplug_max(); - if (query.largest_available_block < (max_addr >> page_shift)) { - dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u " - "%llu-sized pages\n", max_addr, query.largest_available_block, - 1ULL << page_shift); + + page_shift = iommu_get_page_shift(query.page_size); + if (!page_shift) { + dev_dbg(&dev->dev, "no supported page size in mask %x", + query.page_size); goto out_failed; } - len = order_base_2(max_addr); - win64 = kzalloc(sizeof(struct property), GFP_KERNEL); - if (!win64) { - dev_info(&dev->dev, - "couldn't allocate property for 64bit dma window\n"); - goto out_failed; + + + /* + * The "ibm,pmemory" can appear anywhere in the address space. + * Assuming it is still backed by page structs, try MAX_PHYSMEM_BITS + * for the upper limit and fallback to max RAM otherwise but this + * disables device::dma_ops_bypass. + */ + len = max_ram_len; + if (pmem_present) { + if (query.largest_available_block >= + (1ULL << (MAX_PHYSMEM_BITS - page_shift))) + len = MAX_PHYSMEM_BITS; + else + dev_info(&dev->dev, "Skipping ibm,pmemory"); } - win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL); - win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL); - win64->length = sizeof(*ddwprop); - if (!win64->name || !win64->value) { - dev_info(&dev->dev, - "couldn't allocate property name and value\n"); - goto out_free_prop; + + /* check if the available block * number of ptes will map everything */ + if (query.largest_available_block < (1ULL << (len - page_shift))) { + dev_dbg(&dev->dev, + "can't map partition max 0x%llx with %llu %llu-sized pages\n", + 1ULL << len, + query.largest_available_block, + 1ULL << page_shift); + + len = order_base_2(query.largest_available_block << page_shift); + win_name = DMA64_PROPNAME; + } else { + direct_mapping = !default_win_removed || + (len == MAX_PHYSMEM_BITS) || + (!pmem_present && (len == max_ram_len)); + win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME; } ret = create_ddw(dev, ddw_avail, &create, page_shift, len); if (ret != 0) - goto out_free_prop; - - ddwprop->liobn = cpu_to_be32(create.liobn); - ddwprop->dma_base = cpu_to_be64(((u64)create.addr_hi << 32) | - create.addr_lo); - ddwprop->tce_shift = cpu_to_be32(page_shift); - ddwprop->window_shift = cpu_to_be32(len); + goto out_failed; dev_dbg(&dev->dev, "created tce table LIOBN 0x%x for %pOF\n", create.liobn, dn); - window = kzalloc(sizeof(*window), GFP_KERNEL); - if (!window) - goto out_clear_window; + win_addr = ((u64)create.addr_hi << 32) | create.addr_lo; + win64 = ddw_property_create(win_name, create.liobn, win_addr, page_shift, len); - ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT, - win64->value, tce_setrange_multi_pSeriesLP_walk); - if (ret) { - dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n", - dn, ret); - goto out_free_window; + if (!win64) { + dev_info(&dev->dev, + "couldn't allocate property, property name, or value\n"); + goto out_remove_win; } ret = of_add_property(pdn, win64); if (ret) { - dev_err(&dev->dev, "unable to add dma window property for %pOF: %d", - pdn, ret); - goto out_free_window; + dev_err(&dev->dev, "unable to add DMA window property for %pOF: %d", + pdn, ret); + goto out_free_prop; } - window->device = pdn; - window->prop = ddwprop; - spin_lock(&direct_window_list_lock); - list_add(&window->list, &direct_window_list); - spin_unlock(&direct_window_list_lock); + window = ddw_list_new_entry(pdn, win64->value); + if (!window) + goto out_del_prop; + + if (direct_mapping) { + /* DDW maps the whole partition, so enable direct DMA mapping */ + ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT, + win64->value, tce_setrange_multi_pSeriesLP_walk); + if (ret) { + dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n", + dn, ret); + + /* Make sure to clean DDW if any TCE was set*/ + clean_dma_window(pdn, win64->value); + goto out_del_list; + } + } else { + struct iommu_table *newtbl; + int i; + unsigned long start = 0, end = 0; + + for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) { + const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM; + + /* Look for MMIO32 */ + if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) { + start = pci->phb->mem_resources[i].start; + end = pci->phb->mem_resources[i].end; + break; + } + } + + /* New table for using DDW instead of the default DMA window */ + newtbl = iommu_pseries_alloc_table(pci->phb->node); + if (!newtbl) { + dev_dbg(&dev->dev, "couldn't create new IOMMU table\n"); + goto out_del_list; + } + + iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr, + 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops); + iommu_init_table(newtbl, pci->phb->node, start, end); + + pci->table_group->tables[1] = newtbl; + + set_iommu_table_base(&dev->dev, newtbl); + } + + if (default_win_removed) { + iommu_tce_table_put(pci->table_group->tables[0]); + pci->table_group->tables[0] = NULL; + + /* default_win is valid here because default_win_removed == true */ + of_remove_property(pdn, default_win); + dev_info(&dev->dev, "Removed default DMA window for %pOF\n", pdn); + } + + spin_lock(&dma_win_list_lock); + list_add(&window->list, &dma_win_list); + spin_unlock(&dma_win_list_lock); - dma_addr = be64_to_cpu(ddwprop->dma_base); + dev->dev.archdata.dma_offset = win_addr; goto out_unlock; -out_free_window: +out_del_list: kfree(window); -out_clear_window: - remove_ddw(pdn, true); +out_del_prop: + of_remove_property(pdn, win64); out_free_prop: kfree(win64->name); kfree(win64->value); kfree(win64); +out_remove_win: + /* DDW is clean, so it's ok to call this directly. */ + __remove_dma_window(pdn, ddw_avail, create.liobn); + out_failed: + if (default_win_removed) + reset_dma_window(dev, pdn); fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL); if (!fpdn) @@ -1141,8 +1494,17 @@ out_failed: list_add(&fpdn->list, &failed_ddw_pdn_list); out_unlock: - mutex_unlock(&direct_window_init_mutex); - return dma_addr; + mutex_unlock(&dma_win_init_mutex); + + /* + * If we have persistent memory and the window size is only as big + * as RAM, then we failed to create a window to cover persistent + * memory and need to set the DMA limit. + */ + if (pmem_present && direct_mapping && len == max_ram_len) + dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len); + + return direct_mapping; } static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) @@ -1163,13 +1525,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn); - for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group; - pdn = pdn->parent) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - if (dma_window) - break; - } - + pdn = pci_dma_find(dn, &dma_window); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1184,7 +1540,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) tbl = pci->table_group->tables[0]; iommu_table_setparms_lpar(pci->phb, pdn, tbl, pci->table_group, dma_window); - tbl->it_ops = &iommu_table_lpar_multi_ops; + iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, pci_domain_nr(pci->phb->bus), 0); @@ -1200,7 +1556,6 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask) { struct device_node *dn = pci_device_to_OF_node(pdev), *pdn; - const __be32 *dma_window = NULL; /* only attempt to use a new window if 64-bit DMA is requested */ if (dma_mask < DMA_BIT_MASK(64)) @@ -1214,18 +1569,9 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask) * search upwards in the tree until we either hit a dma-window * property, OR find a parent with a table already allocated. */ - for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group; - pdn = pdn->parent) { - dma_window = of_get_property(pdn, "ibm,dma-window", NULL); - if (dma_window) - break; - } - - if (pdn && PCI_DN(pdn)) { - pdev->dev.archdata.dma_offset = enable_ddw(pdev, pdn); - if (pdev->dev.archdata.dma_offset) - return true; - } + pdn = pci_dma_find(dn, NULL); + if (pdn && PCI_DN(pdn)) + return enable_ddw(pdev, pdn); return false; } @@ -1233,29 +1579,29 @@ static bool iommu_bypass_supported_pSeriesLP(struct pci_dev *pdev, u64 dma_mask) static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { - struct direct_window *window; + struct dma_win *window; struct memory_notify *arg = data; int ret = 0; switch (action) { case MEM_GOING_ONLINE: - spin_lock(&direct_window_list_lock); - list_for_each_entry(window, &direct_window_list, list) { + spin_lock(&dma_win_list_lock); + list_for_each_entry(window, &dma_win_list, list) { ret |= tce_setrange_multi_pSeriesLP(arg->start_pfn, arg->nr_pages, window->prop); /* XXX log error */ } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); break; case MEM_CANCEL_ONLINE: case MEM_OFFLINE: - spin_lock(&direct_window_list_lock); - list_for_each_entry(window, &direct_window_list, list) { + spin_lock(&dma_win_list_lock); + list_for_each_entry(window, &dma_win_list, list) { ret |= tce_clearrange_multi_pSeriesLP(arg->start_pfn, arg->nr_pages, window->prop); /* XXX log error */ } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); break; default: break; @@ -1276,7 +1622,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti struct of_reconfig_data *rd = data; struct device_node *np = rd->dn; struct pci_dn *pci = PCI_DN(np); - struct direct_window *window; + struct dma_win *window; switch (action) { case OF_RECONFIG_DETACH_NODE: @@ -1287,20 +1633,22 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti * we have to remove the property when releasing * the device node. */ - remove_ddw(np, false); + if (remove_ddw(np, false, DIRECT64_PROPNAME)) + remove_ddw(np, false, DMA64_PROPNAME); + if (pci && pci->table_group) iommu_pseries_free_group(pci->table_group, np->full_name); - spin_lock(&direct_window_list_lock); - list_for_each_entry(window, &direct_window_list, list) { + spin_lock(&dma_win_list_lock); + list_for_each_entry(window, &dma_win_list, list) { if (window->device == np) { list_del(&window->list); kfree(window); break; } } - spin_unlock(&direct_window_list_lock); + spin_unlock(&dma_win_list_lock); break; default: err = NOTIFY_DONE; @@ -1314,7 +1662,7 @@ static struct notifier_block iommu_reconfig_nb = { }; /* These are called very early. */ -void iommu_init_early_pSeries(void) +void __init iommu_init_early_pSeries(void) { if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL)) return; |